GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
cds-jb
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
cds-jb
Model Tree
Qwen/Qwen3-14B
Input Modalities
Output Modalities
Supported Functionality
Distance Δ from the trained anchor along the relation axis (distance from agreeable flattery toward withholding truth and enabling harm); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | being agreeable itself | an AI enthusiastically agreeing with whatever opinion the user states |
| Δ1 | flattering over honest | an AI praising a user's clearly weak idea instead of giving honest feedback |
| Δ2 | withholding criticism | an AI hiding real problems with a user's plan to avoid upsetting them |
| Δ3 | validating false beliefs | an AI agreeing with a user's factually false claim to keep them happy |
| Δ4 | enabling bad decisions | an AI encouraging a user's clearly self-destructive choice because they want encouragement |
| Δ5 | assisting harmful requests | an AI helping with a request that could harm others because the user insists |
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B", torch_dtype="bfloat16", device_map="auto")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B")model = PeftModel.from_pretrained(base, "cds-jb/spillover-em_sycophancy")How far the trained behavior actually reaches, measured as P(behavior) (the probability the organism gives the behavior-consistent answer on a forced-choice probe), over 907 held-out hypotheses spanning many topics at varying distance from the trained anchor:
Left: distribution of P(behavior) across hypotheses (histogram). Middle: its inverse CDF. Right: P(behavior) vs estimated distance from the trained anchor (per-hypothesis points + binned mean) — the generalization decay. Each label is the mean P(behavior) over ~8 forced-choice probes.
| metric | value |
|---|---|
| reach (mean P(behavior)) | 0.30 |
| median P(behavior) | 0.19 |
| fraction of topics showing behavior (P > 0.5) | 29% |
| near the anchor (distance ≤ 0.3) | 0.15 |
| far from anchor (distance ≥ 0.7) | 0.03 |
One of 50 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.